Group 14 - Project FP01¶

Time series anomaly detection - LSTM-ED¶

In [ ]:
import time
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import tensorflow as tf

from dataset import *
from plots import *
from metrics import *
from models_functions import *

# Set style for matplotlib
plt.style.use("Solarize_Light2")

import plotly.io as pio
pio.renderers.default = "notebook_connected"
WARNING:tensorflow:From c:\Users\VG User\Documents\GitHub\MLinAPP-FP01-14\.venv\Lib\site-packages\keras\src\losses.py:2976: The name tf.losses.sparse_softmax_cross_entropy is deprecated. Please use tf.compat.v1.losses.sparse_softmax_cross_entropy instead.

In [ ]:
# Path to the root directory of the dataset
ROOTDIR_DATASET_NORMAL =  '../dataset/normal'
ROOTDIR_DATASET_ANOMALY = '../dataset/collisions'

# TF_ENABLE_ONEDNN_OPTS=0 means that the model will not use the oneDNN library for optimization

import os
os.environ['TF_ENABLE_ONEDNN_OPTS'] = '0'

Various parameters¶

In [ ]:
#freq = '1.0'
#freq = '0.1'
#freq = '0.01'
freq = '0.005'

file_name_normal = "_20220811_rbtc_"
file_name_collisions = "_collision_20220811_rbtc_"

recording_normal = [0, 2, 3, 4]
recording_collisions = [1, 5]

freq_str = freq.replace(".", "_")
features_folder_normal = f"./features/normal{freq_str}/"
features_folder_collisions = f"./features/collisions{freq_str}/"

Data¶

In [ ]:
df_features_normal, df_normal_raw, _ = get_dataframes(ROOTDIR_DATASET_NORMAL, file_name_normal, recording_normal, freq, None)
df_features_collisions, df_collisions_raw, df_collisions_raw_action = get_dataframes(ROOTDIR_DATASET_ANOMALY, file_name_collisions, recording_collisions, freq, None)
df_features_collisions_1, df_collisions_raw_1, df_collisions_raw_action_1 = get_dataframes(ROOTDIR_DATASET_ANOMALY, file_name_collisions, [1], freq, None)
df_features_collisions_5, df_collisions_raw_5, df_collisions_raw_action_5 = get_dataframes(ROOTDIR_DATASET_ANOMALY, file_name_collisions, [5], freq, None)
Loading data.
Found 31 different actions.
Loading data done.

Computing features.

Progress: 0% Complete

0

Skipped feature extraction for pickFromPallet(1,2)=[true,1,0] 2022-08-11 14:37:37.436000 : 2022-08-11 14:37:37.421000.
Skipped feature extraction for placeToPallet(1,1)=[true,0] 2022-08-11 14:37:37.421000 : 2022-08-11 14:37:37.442000.
Skipped feature extraction for pickFromPallet(3,2)=[true,1,0] 2022-08-11 15:36:32.568000 : 2022-08-11 15:36:32.533000.
Skipped feature extraction for pickFromPallet(3,2)=[true,1,0] 2022-08-11 15:36:32.572000 : 2022-08-11 15:36:32.561000.
Skipped feature extraction for placeToPallet(1,3)=[true,0] 2022-08-11 15:36:32.533000 : 2022-08-11 15:36:32.572000.
Skipped feature extraction for placeToPallet(1,3)=[true,0] 2022-08-11 15:36:32.561000 : 2022-08-11 15:36:32.561000.
--- 118.75116038322449 seconds ---
Loading data.
Found 31 different actions.
Loading data done.

Computing features.

Progress: 0% Complete

0

Skipped feature extraction for moveOverPallet(1,3)=[true,0] 2022-08-11 16:55:15.149000 : 2022-08-11 16:55:15.146000.
Skipped feature extraction for moveOverPallet(3,1)=[true,0] 2022-08-11 16:55:15.146000 : 2022-08-11 16:55:15.150000.
--- 43.83658695220947 seconds ---
Loading data.
Found 31 different actions.
Loading data done.

Computing features.

Progress: 0% Complete

0

--- 21.850510597229004 seconds ---
Loading data.
Found 31 different actions.
Loading data done.

Computing features.

Progress: 0% Complete

0

Skipped feature extraction for moveOverPallet(1,3)=[true,0] 2022-08-11 16:55:15.149000 : 2022-08-11 16:55:15.146000.
Skipped feature extraction for moveOverPallet(3,1)=[true,0] 2022-08-11 16:55:15.146000 : 2022-08-11 16:55:15.150000.
--- 25.490682125091553 seconds ---
In [ ]:
# df_features_normal, df_normal_raw, _ = get_dataframes(ROOTDIR_DATASET_NORMAL, file_name_normal, recording_normal, freq, f"{features_folder_normal}")
# df_features_collisions, df_collisions_raw, df_collisions_raw_action = get_dataframes(ROOTDIR_DATASET_ANOMALY, file_name_collisions, recording_collisions, freq, f"{features_folder_collisions}1_5/")
# df_features_collisions_1, df_collisions_raw_1, df_collisions_raw_action_1 = get_dataframes(ROOTDIR_DATASET_ANOMALY, file_name_collisions, [1], freq, f"{features_folder_collisions}1/")
# df_features_collisions_5, df_collisions_raw_5, df_collisions_raw_action_5 = get_dataframes(ROOTDIR_DATASET_ANOMALY, file_name_collisions, [5], freq, f"{features_folder_collisions}5/")
In [ ]:
X_train, y_train, X_test, y_test, df_test = get_train_test_data(df_features_normal, df_features_collisions, full_normal=True)
X_train_1, y_train_1, X_test_1, y_test_1, df_test_1 = get_train_test_data(df_features_normal, df_features_collisions_1, full_normal=True)
X_train_5, y_train_5, X_test_5, y_test_5, df_test_5 = get_train_test_data(df_features_normal, df_features_collisions_5, full_normal=True)

Collisions¶

In [ ]:
collisions_rec1, collisions_init1 = get_collisions('1', ROOTDIR_DATASET_ANOMALY)
collisions_rec5, collisions_init5 = get_collisions('5', ROOTDIR_DATASET_ANOMALY)

# Merge the collisions of the two recordings in one dataframe
collisions_rec = pd.concat([collisions_rec1, collisions_rec5])
collisions_init = pd.concat([collisions_init1, collisions_init5])
In [ ]:
collisions_zones, y_collisions = get_collisions_zones_and_labels(collisions_rec, collisions_init, df_features_collisions)
collisions_zones_1, y_collisions_1 = get_collisions_zones_and_labels(collisions_rec1, collisions_init1, df_features_collisions_1)
collisions_zones_5, y_collisions_5 = get_collisions_zones_and_labels(collisions_rec5, collisions_init5, df_features_collisions_5)

LSTM-ED for Anomaly Detection in Time Series Data¶

In [ ]:
from algorithms.lstm_enc_dec_axl import LSTMED

classifier = LSTMED(
    name='LSTM-ED',
    num_epochs=50,
    batch_size=64,
    lr=1e-3,
    hidden_size=64,
    sequence_length=100,
    train_gaussian_percentage=0.30,
    n_layers=(2, 2),
    use_bias=(True, True),
    dropout=(0.1, 0.1),
    seed=42,
    gpu=None,              # Set to None for CPU, or specify GPU index if available
    details=True
)
# Train the LSTM on normal data
classifier.fit(X_train)
print("LSTM-ED training completed.")
100%|██████████| 50/50 [01:37<00:00,  1.94s/it]
LSTM-ED training completed.

Predictions¶

In [ ]:
df_test = get_statistics(X_test, y_collisions, classifier, df_test, freq, threshold_type="mad")
df_test_1 = get_statistics(X_test_1, y_collisions_1, classifier, df_test_1, freq, threshold_type="mad")
df_test_5 = get_statistics(X_test_5, y_collisions_5, classifier, df_test_5, freq, threshold_type="mad")
Anomaly prediction completed.
Number of anomalies detected: 1 with threshold 13084435615.576904, std
Number of anomalies detected: 118 with threshold 162.9702962940295, mad
Number of anomalies detected: 16 with threshold 779.0025365561331, percentile
Number of anomalies detected: 6 with threshold 1014.7057885453083, IQR
Number of anomalies detected: 306 with threshold 0.0, zero

choosen threshold type: mad, with value: 162.9703
F1 Score: 0.9417
Accuracy: 0.9575
Precision: 0.8898
Recall: 1.0000
              precision    recall  f1-score   support

           0       1.00      0.94      0.97       201
           1       0.89      1.00      0.94       105

    accuracy                           0.96       306
   macro avg       0.94      0.97      0.95       306
weighted avg       0.96      0.96      0.96       306

ROC AUC Score: 0.9774
No description has been provided for this image
No description has been provided for this image
No description has been provided for this image
Anomalies detected: 118
Best threshold: 173.4108 | F1 Score: 0.9417 | Precision: 0.8898 | Recall: 1.0000
Anomalies detected with best threshold: 118

	-------------------------------------------------------------------------------------

Anomaly prediction completed.
Number of anomalies detected: 1 with threshold 18030223610.182114, std
Number of anomalies detected: 45 with threshold 139.055142476544, mad
Number of anomalies detected: 9 with threshold 717.5305852775556, percentile
Number of anomalies detected: 31 with threshold 245.15972109615694, IQR
Number of anomalies detected: 164 with threshold 0.0, zero

choosen threshold type: mad, with value: 139.0551
F1 Score: 0.8750
Accuracy: 0.9390
Precision: 0.7778
Recall: 1.0000
              precision    recall  f1-score   support

           0       1.00      0.92      0.96       129
           1       0.78      1.00      0.88        35

    accuracy                           0.94       164
   macro avg       0.89      0.96      0.92       164
weighted avg       0.95      0.94      0.94       164

ROC AUC Score: 0.9805
No description has been provided for this image
No description has been provided for this image
No description has been provided for this image
Anomalies detected: 45
Best threshold: 184.9405 | F1 Score: 0.9067 | Precision: 0.8500 | Recall: 0.9714
Anomalies detected with best threshold: 40

	-------------------------------------------------------------------------------------

Anomaly prediction completed.
Number of anomalies detected: 2 with threshold 1018.983006434978, std
Number of anomalies detected: 25 with threshold 648.9818858885125, mad
Number of anomalies detected: 8 with threshold 844.7135347042098, percentile
Number of anomalies detected: 2 with threshold 1329.8081279069997, IQR
Number of anomalies detected: 141 with threshold 0.0, zero

choosen threshold type: mad, with value: 648.9819
F1 Score: 0.5432
Accuracy: 0.7376
Precision: 0.8800
Recall: 0.3929
              precision    recall  f1-score   support

           0       0.71      0.96      0.82        85
           1       0.88      0.39      0.54        56

    accuracy                           0.74       141
   macro avg       0.79      0.68      0.68       141
weighted avg       0.78      0.74      0.71       141

ROC AUC Score: 0.9538
No description has been provided for this image
No description has been provided for this image
No description has been provided for this image
Anomalies detected: 25
Best threshold: 424.2105 | F1 Score: 0.9231 | Precision: 0.8852 | Recall: 0.9643
Anomalies detected with best threshold: 61

	-------------------------------------------------------------------------------------

In [ ]:
plot_anomalies_true_and_predicted(df_collisions_raw, df_collisions_raw_action, collisions_zones, df_test, title="Collisions zones vs predicted zones for both recordings")
In [ ]:
plot_anomalies_true_and_predicted(df_collisions_raw_1, df_collisions_raw_action_1, collisions_zones_1, df_test_1, title="Collisions zones vs predicted zones for recording 1")
In [ ]:
plot_anomalies_true_and_predicted(df_collisions_raw_5, df_collisions_raw_action_5, collisions_zones_5, df_test_5, title="Collisions zones vs predicted zones for recording 5")